@inproceedings{yanan-etal-2021-category,
title = "Category-Based Strategy-Driven Question Generator for Visual Dialogue",
author = "Yanan, Shi and
Yanxin, Tan and
Fangxiang, Feng and
Chunping, Zheng and
Xiaojie, Wang",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.89",
pages = "1000--1011",
abstract = "GuessWhat?! is a task-oriented visual dialogue task which has two players a guesser and anoracle. Guesser aims to locate the object supposed by oracle by asking several Yes/No questions which are answered by oracle. How to ask proper questions is crucial to achieve the final goal of the whole task. Previous methods generally use an word-level generator which is hard to grasp the dialogue-level questioning strategy. They often generate repeated or useless questions. This paper proposes a sentence-level category-based strategy-driven question generator(CSQG) to explicitly provide a category based questioning strategy for the generator. First we encode the image and the dialogue history to decide the category of the next question to be generated. Thenthe question is generated with the helps of category-based dialogue strategy as well as encoding of both the image and dialogue history. The evaluation on large-scale visual dialogue dataset GuessWhat?! shows that our method can help guesser achieve 51.71{\%} success rate which is the state-of-the-art on the supervised training methods.",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yanan-etal-2021-category">
<titleInfo>
<title>Category-Based Strategy-Driven Question Generator for Visual Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Yanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tan</namePart>
<namePart type="family">Yanxin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Fangxiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Chunping</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Xiaojie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>GuessWhat?! is a task-oriented visual dialogue task which has two players a guesser and anoracle. Guesser aims to locate the object supposed by oracle by asking several Yes/No questions which are answered by oracle. How to ask proper questions is crucial to achieve the final goal of the whole task. Previous methods generally use an word-level generator which is hard to grasp the dialogue-level questioning strategy. They often generate repeated or useless questions. This paper proposes a sentence-level category-based strategy-driven question generator(CSQG) to explicitly provide a category based questioning strategy for the generator. First we encode the image and the dialogue history to decide the category of the next question to be generated. Thenthe question is generated with the helps of category-based dialogue strategy as well as encoding of both the image and dialogue history. The evaluation on large-scale visual dialogue dataset GuessWhat?! shows that our method can help guesser achieve 51.71% success rate which is the state-of-the-art on the supervised training methods.</abstract>
<identifier type="citekey">yanan-etal-2021-category</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.89</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1000</start>
<end>1011</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Category-Based Strategy-Driven Question Generator for Visual Dialogue
%A Yanan, Shi
%A Yanxin, Tan
%A Fangxiang, Feng
%A Chunping, Zheng
%A Xiaojie, Wang
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G English
%F yanan-etal-2021-category
%X GuessWhat?! is a task-oriented visual dialogue task which has two players a guesser and anoracle. Guesser aims to locate the object supposed by oracle by asking several Yes/No questions which are answered by oracle. How to ask proper questions is crucial to achieve the final goal of the whole task. Previous methods generally use an word-level generator which is hard to grasp the dialogue-level questioning strategy. They often generate repeated or useless questions. This paper proposes a sentence-level category-based strategy-driven question generator(CSQG) to explicitly provide a category based questioning strategy for the generator. First we encode the image and the dialogue history to decide the category of the next question to be generated. Thenthe question is generated with the helps of category-based dialogue strategy as well as encoding of both the image and dialogue history. The evaluation on large-scale visual dialogue dataset GuessWhat?! shows that our method can help guesser achieve 51.71% success rate which is the state-of-the-art on the supervised training methods.
%U https://aclanthology.org/2021.ccl-1.89
%P 1000-1011
Markdown (Informal)
[Category-Based Strategy-Driven Question Generator for Visual Dialogue](https://aclanthology.org/2021.ccl-1.89) (Yanan et al., CCL 2021)
ACL